Matches in SemOpenAlex for { <https://semopenalex.org/work/W2584508293> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2584508293 abstract "The multi-level adaptive networks (MLAN) technique is a cross-lingual adaptation framework where a bottleneck (BN) layer in a deep neural network (DNN) trained in a source lan- guage is used for producing BN features to be exploited in a second DNN in a target language. We investigate how the correlation (in the sense of phonetic similarity) of the source and target languages and the amount of data of the source language affect the efficiency of the MLAN schemes. We experiment with three different scenarios using, i) French, as a source language uncorrelated to the target language, ii) Ukrainian, as a source language correlated to the target one and finally iii) English as a source language uncorrelated to the target language using a relatively large amount of data in respect to the other two scenarios. In all cases Russian is used as target language. GLOBALPHONE data is used, except for English, where a mixture of LIBRISPEECH, TEDLIUM and AMIDA is available. The results have shown that both of these two factors are important for the MLAN schemes. Specifically, on the one hand, when a modest amount of data from the source language is used, the correlation of the source and target languages is very important. On the other hand, the correlation of the two languages seems to be less important when a relatively large amount of data, from the source language, is used. The best performance in word error rate (WER), was achieved when the English language was used as the source one in the multi-task MLAN scheme, achieving a relative improvement of 9.4% in respect to the baseline DNN model." @default.
- W2584508293 created "2017-02-10" @default.
- W2584508293 creator A5016006232 @default.
- W2584508293 creator A5039529498 @default.
- W2584508293 creator A5065066165 @default.
- W2584508293 creator A5076409146 @default.
- W2584508293 creator A5081808619 @default.
- W2584508293 date "2016-01-01" @default.
- W2584508293 modified "2023-09-26" @default.
- W2584508293 title "Investigating Cross-lingual Multi-level Adaptive Networks: The Importance of the Correlation of Source and Target Languages" @default.
- W2584508293 cites W1494198834 @default.
- W2584508293 cites W1524333225 @default.
- W2584508293 cites W1537275613 @default.
- W2584508293 cites W1994606281 @default.
- W2584508293 cites W2025198378 @default.
- W2584508293 cites W2062164080 @default.
- W2584508293 cites W2084534958 @default.
- W2584508293 cites W2085313529 @default.
- W2584508293 cites W2121573996 @default.
- W2584508293 cites W2127982613 @default.
- W2584508293 cites W2146871184 @default.
- W2584508293 cites W2172130635 @default.
- W2584508293 cites W2250357346 @default.
- W2584508293 cites W2406395231 @default.
- W2584508293 cites W2407240503 @default.
- W2584508293 cites W3203261311 @default.
- W2584508293 cites W66627554 @default.
- W2584508293 cites W82936479 @default.
- W2584508293 hasPublicationYear "2016" @default.
- W2584508293 type Work @default.
- W2584508293 sameAs 2584508293 @default.
- W2584508293 citedByCount "0" @default.
- W2584508293 crossrefType "journal-article" @default.
- W2584508293 hasAuthorship W2584508293A5016006232 @default.
- W2584508293 hasAuthorship W2584508293A5039529498 @default.
- W2584508293 hasAuthorship W2584508293A5065066165 @default.
- W2584508293 hasAuthorship W2584508293A5076409146 @default.
- W2584508293 hasAuthorship W2584508293A5081808619 @default.
- W2584508293 hasConcept C103278499 @default.
- W2584508293 hasConcept C105795698 @default.
- W2584508293 hasConcept C115961682 @default.
- W2584508293 hasConcept C117220453 @default.
- W2584508293 hasConcept C138885662 @default.
- W2584508293 hasConcept C154945302 @default.
- W2584508293 hasConcept C169345407 @default.
- W2584508293 hasConcept C204321447 @default.
- W2584508293 hasConcept C2524010 @default.
- W2584508293 hasConcept C28490314 @default.
- W2584508293 hasConcept C33923547 @default.
- W2584508293 hasConcept C41008148 @default.
- W2584508293 hasConcept C41895202 @default.
- W2584508293 hasConcept C50644808 @default.
- W2584508293 hasConcept C90805587 @default.
- W2584508293 hasConceptScore W2584508293C103278499 @default.
- W2584508293 hasConceptScore W2584508293C105795698 @default.
- W2584508293 hasConceptScore W2584508293C115961682 @default.
- W2584508293 hasConceptScore W2584508293C117220453 @default.
- W2584508293 hasConceptScore W2584508293C138885662 @default.
- W2584508293 hasConceptScore W2584508293C154945302 @default.
- W2584508293 hasConceptScore W2584508293C169345407 @default.
- W2584508293 hasConceptScore W2584508293C204321447 @default.
- W2584508293 hasConceptScore W2584508293C2524010 @default.
- W2584508293 hasConceptScore W2584508293C28490314 @default.
- W2584508293 hasConceptScore W2584508293C33923547 @default.
- W2584508293 hasConceptScore W2584508293C41008148 @default.
- W2584508293 hasConceptScore W2584508293C41895202 @default.
- W2584508293 hasConceptScore W2584508293C50644808 @default.
- W2584508293 hasConceptScore W2584508293C90805587 @default.
- W2584508293 hasLocation W25845082931 @default.
- W2584508293 hasOpenAccess W2584508293 @default.
- W2584508293 hasPrimaryLocation W25845082931 @default.
- W2584508293 hasRelatedWork W1985349217 @default.
- W2584508293 hasRelatedWork W1999065145 @default.
- W2584508293 hasRelatedWork W2001068000 @default.
- W2584508293 hasRelatedWork W2013205774 @default.
- W2584508293 hasRelatedWork W2099791461 @default.
- W2584508293 hasRelatedWork W2105076537 @default.
- W2584508293 hasRelatedWork W2115456980 @default.
- W2584508293 hasRelatedWork W2146353824 @default.
- W2584508293 hasRelatedWork W2151348424 @default.
- W2584508293 hasRelatedWork W2153338568 @default.
- W2584508293 hasRelatedWork W2158076977 @default.
- W2584508293 hasRelatedWork W2169731540 @default.
- W2584508293 hasRelatedWork W2188071247 @default.
- W2584508293 hasRelatedWork W2242045876 @default.
- W2584508293 hasRelatedWork W2562038989 @default.
- W2584508293 hasRelatedWork W2926989360 @default.
- W2584508293 hasRelatedWork W2949174760 @default.
- W2584508293 hasRelatedWork W3003809177 @default.
- W2584508293 hasRelatedWork W3213809193 @default.
- W2584508293 hasRelatedWork W574924521 @default.
- W2584508293 isParatext "false" @default.
- W2584508293 isRetracted "false" @default.
- W2584508293 magId "2584508293" @default.
- W2584508293 workType "article" @default.